Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 614 for “"learning problems"”.
-
Bayesian Designs For Sequential Learning Problems
… consider the Bayesian formulation of a number of learning problems, where we focus on sequential sampling procedures for allocating simulation effort efficiently. We derive Bayes-optimal policies for the problem of multiple comparisons with a known standard, showing that they can be computed …
-
Practical optimization for structured machine learning problems
… years have witnessed huge advances in machine learning (ML) and its applications, especially in image, speech, and language applications. Optimization in ML is a key ingredient in both the training and hyperparameter tuning steps, and it also influences the test phase. In this thesis, we make …
-
Computation Approaches for Continuous Reinforcement Learning Problems
… system through a set of actions. Linear control problems have been extensively studied, and optimal control laws have been identified. But the world around us is highly non-linear and unpredictable. For these dynamic systems, which don’t possess the nice mathematical properties of the linear …
-
Information-Theoretic Measures in Selected Learning Problems
… the usage of information-theoretic measures in learning problems. The first problem considered is the algorithm-dependent generalization error bound. Conceptually, the mutual information between the output of the learning algorithm and training samples captures the amount of information the …
-
Learning Problems Related to Stochastic Differential Equations
… develops a Bayesian framework for nonparametric learning in SDEs, addressing key challenges in inference, particularly when dealing with complex systems and incomplete data. The thesis begins by establishing a theoretical foundation in optimization over Hilbert spaces, including a generalized …
-
Inducing succinct rules in machine learning problems
Machine Learning techniques, in particular induction algorithms, have been applied to the field of expert systems development in an effort to overcome the knowledge acquisition bottleneck. Many different induction algorithms have been developed. These utilise a number of different knowledge …
-
Certifying robustness in inference and learning problems
… for inference, prediction, and decision-making problems when the underlying distributions governing the data are known and well-modeled. The research from the past few decades has provided powerful learning algorithms when such distributions cannot be easily modeled, for instance with high …
-
Provable alternating minimization for non-convex learning problems
… term for a widely popular approach in non-convex learning: often, it is possible to partition the variables into two (or more) sets, so that the problem is convex/tractable in one set if the other is held fixed (and vice versa). This allows for alternating between optimally updating one set of …
-
EXPLOITING GRADIENT INFORMATION FOR MODERN MACHINE LEARNING PROBLEMS
Many deep learning achievements are attributed to the back-propagation (BP) algorithm, which exploits gradient information of the deep neural network (DNN) models: BP efficiently computes the gradient of the loss function with respect to the weights of a DNN for a batch of examples, and such …
-
Some Continuous-Time Reinforcement Learning Problems in Finance
Reinforcement Learning (RL) is an emerging technique to solve for optimal policies of sequential decision-making problems, particularly when the parameters of the dynamic environment are unknown. Classical RL is framed under a discrete-time setting, often modeled on a Markov Decision Process. While …
-
ALGORITHMS FOR CLUSTERING AND ROBUST UNSUPERVISED LEARNING PROBLEMS
… for clustering and robust unsupervised learning. Specifically, a significant part of this thesis is dedicated to the problem of emph{semi-supervised cluster recovery}. Given a finite set of $n$ points partitioned according to an unknown clustering, the goal is to recover the unknown …
-
Efficient Optimization Algorithms for Nonconvex Machine Learning Problems
… superior performance. These powerful machine learning models have enabled the creation of remarkable AI products. Optimization, as the core of machine learning, becomes especially crucial because most machine learning problems can ultimately be formulated as optimization problems, which …
-
NEW EFFICIENT ALGORITHMS FOR NESTED MACHINE LEARNING PROBLEMS
In recent years, machine learning (ML) has achieved remarkable success by training large-scale models on vast datasets. However, building these models involves multiple interdependent tasks-such as data selection, hyperparameter tuning, and model architecture search-that can lead to nested …
-
New Geometric Approaches for Several Machine Learning Problems
… found applications in many different real world problems– both theoretical and applicational ones. In this dissertation, we apply geometric techniques to multiple problems, including traditional machine learning problems, deep learning related problems, and a biological problem that can be …
-
The Role of Memory in Rule Learning Problems
Thirty-six college subjects who had taken a memory test from the Wechsler series were chosen from an introductory psychology class and divided into three memory levels (high, medium, and low). Twelve subjects from each of the memory groups were required to categorized geometrical stimulus patterns …
-
Efficient non-convex algorithms for large-scale learning problems
… has led to a huge interest in the problem of learning hidden complex structures. Not only can models from such structures fit the datasets, they also have good generalization performance in the regime where the number of samples are limited compared to the dimensionality. However, one of the …
-
A Unified Robust Minimax Framework for Regularized Learning Problems
… to apply minimax related concepts to real-world learning tasks, we develop a new fault-tolerant classification framework to combat class noise for general multi-class classification problems; further, by studying the relationship between the majorizable function class and the minimax framework, …
-
OPERATIONS RESEARCH POWERED APPROACHES TO SEVERAL MACHINE LEARNING PROBLEMS
Adoption of Machine Learning (ML) methods peaked in recent years due to increased hardware capacity and popularity of Large Language Models (LLMs). Although one of the most prominent aspects of ML is automating decisions and systems, this dissertation demonstrates that it is possible to improve ML …
Page 1 of 31